Analysis of -Laplacian Regularization in Semisupervised Learning

D Slepcev, M Thorpe - SIAM Journal on Mathematical Analysis, 2019 - SIAM
We investigate a family of regression problems in a semisupervised setting. The task is to
assign real-valued labels to a set of n sample points provided a small training subset of N …

A variational approach to the consistency of spectral clustering

NG Trillos, D Slepčev - Applied and Computational Harmonic Analysis, 2018 - Elsevier
This paper establishes the consistency of spectral approaches to data clustering. We
consider clustering of point clouds obtained as samples of a ground-truth measure. A graph …

Sharper generalization bounds for clustering

S Li, Y Liu - International Conference on Machine Learning, 2021 - proceedings.mlr.press
Existing generalization analysis of clustering mainly focuses on specific instantiations, such
as (kernel) $ k $-means, and a unified framework for studying clustering performance is still …

Consistency of Cheeger and ratio graph cuts

NG Trillos, D Slep, J Von Brecht, T Laurent… - Journal of Machine …, 2016 - jmlr.org
This paper establishes the consistency of a family of graph-cut-based algorithms for
clustering of data clouds. We consider point clouds obtained as samples of a ground-truth …

Generalization Bounds for Stochastic Gradient Descent via Localized -Covers

S Park, U Simsekli, MA Erdogdu - Advances in Neural …, 2022 - proceedings.neurips.cc
In this paper, we propose a new covering technique localized for the trajectories of SGD.
This localization provides an algorithm-specific complexity measured by the covering …

Large data and zero noise limits of graph-based semi-supervised learning algorithms

MM Dunlop, D Slepčev, AM Stuart, M Thorpe - Applied and Computational …, 2020 - Elsevier
Scalings in which the graph Laplacian approaches a differential operator in the large graph
limit are used to develop understanding of a number of algorithms for semi-supervised …

Centroidal power diagrams, Lloyd's algorithm, and applications to optimal location problems

DP Bourne, SM Roper - SIAM Journal on Numerical Analysis, 2015 - SIAM
In this paper we develop a numerical method for solving a class of optimization problems
known as optimal location or quantization problems. The target energy can be written either …

Uniform Fatou's lemma

EA Feinberg, PO Kasyanov, MZ Zgurovsky - Journal of Mathematical …, 2016 - Elsevier
Fatou's lemma is a classic fact in real analysis stating that the limit inferior of integrals of
functions is greater than or equal to the integral of the inferior limit. This paper introduces a …

Fatou's lemma for weakly converging measures under the uniform integrability condition

EA Feinberg, PO Kasyanov, Y Liang - Theory of Probability & Its Applications, 2020 - SIAM
This paper describes Fatou's lemma for a sequence of measures converging weakly to a
finite measure and for a sequence of functions whose negative parts are uniformly …

Enhancing load balancing by intrusion detection system chain on sdn data plane

N Niknami, J Wu - 2022 IEEE Conference on Communications …, 2022 - ieeexplore.ieee.org
The software-defined network (SDN) allows us to control network flows easily and
dynamically. Intrusion detection systems (IDS) are among the controller's applications. The …